Free price reference

LLM pricing, every model side by side

Cost per million tokens (input, output, and cache), plus context windows, for 3,364 models across every major provider. Prices sync daily from the open LiteLLM dataset. Pick a model for details and a workload cost calculator.

Model Provider ↑ Input /Mtok Output /Mtok Cache read Cache write Context Modality
kimi-k2-thinking-251104
kimi-k2-thinking-251104
Volcengine $0.0000 $0.0000 229,376 text
voyage/rerank-2
voyage/rerank-2
Voyage $0.0500 $0.0000 16,000 rerank
voyage/rerank-2-lite
voyage/rerank-2-lite
Voyage $0.0200 $0.0000 8,000 rerank
voyage/rerank-2.5
voyage/rerank-2.5
Voyage $0.0500 $0.0000 32,000 rerank
voyage/rerank-2.5-lite
voyage/rerank-2.5-lite
Voyage $0.0200 $0.0000 32,000 rerank
voyage/rerank-3
voyage/rerank-3
Voyage $0.0500 $0.0000 32,000 rerank
voyage/rerank-3-lite
voyage/rerank-3-lite
Voyage $0.0200 $0.0000 32,000 rerank
voyage/voyage-2
voyage/voyage-2
Voyage $0.1000 $0.0000 4,000 embedding
voyage/voyage-3
voyage/voyage-3
Voyage $0.0600 $0.0000 32,000 embedding
voyage/voyage-3-large
voyage/voyage-3-large
Voyage $0.1800 $0.0000 32,000 embedding
voyage/voyage-3-lite
voyage/voyage-3-lite
Voyage $0.0200 $0.0000 32,000 embedding
voyage/voyage-3.5
voyage/voyage-3.5
Voyage $0.0600 $0.0000 32,000 embedding
voyage/voyage-3.5-lite
voyage/voyage-3.5-lite
Voyage $0.0200 $0.0000 32,000 embedding
voyage/voyage-4
voyage/voyage-4
Voyage $0.0600 $0.0000 32,000 embedding
voyage/voyage-4-large
voyage/voyage-4-large
Voyage $0.1200 $0.0000 32,000 embedding
voyage/voyage-4-lite
voyage/voyage-4-lite
Voyage $0.0200 $0.0000 32,000 embedding
voyage/voyage-code-2
voyage/voyage-code-2
Voyage $0.1200 $0.0000 16,000 embedding
voyage/voyage-code-3
voyage/voyage-code-3
Voyage $0.1800 $0.0000 32,000 embedding
voyage/voyage-code-4
voyage/voyage-code-4
Voyage $0.1200 $0.0000 32,000 embedding
voyage/voyage-context-3
voyage/voyage-context-3
Voyage $0.1800 $0.0000 120,000 embedding
voyage/voyage-context-4
voyage/voyage-context-4
Voyage $0.1200 $0.0000 120,000 embedding
voyage/voyage-finance-2
voyage/voyage-finance-2
Voyage $0.1200 $0.0000 32,000 embedding
voyage/voyage-large-2
voyage/voyage-large-2
Voyage $0.1200 $0.0000 16,000 embedding
voyage/voyage-law-2
voyage/voyage-law-2
Voyage $0.1200 $0.0000 16,000 embedding
voyage/voyage-lite-01
voyage/voyage-lite-01
Voyage $0.1000 $0.0000 4,096 embedding
voyage/voyage-lite-02-instruct
voyage/voyage-lite-02-instruct
Voyage $0.1000 $0.0000 4,000 embedding
voyage/voyage-multilingual-2
voyage/voyage-multilingual-2
Voyage $0.1200 $0.0000 32,000 embedding
voyage/voyage-multimodal-3
voyage/voyage-multimodal-3
Voyage $0.1200 $0.0000 32,000 embedding
voyage/voyage-multimodal-3.5
voyage/voyage-multimodal-3.5
Voyage $0.1200 $0.0000 32,000 embedding
wandb/deepseek-ai/DeepSeek-R1-0528
wandb/deepseek-ai/DeepSeek-R1-0528
Wandb $1.35 $5.40 161,000 text
wandb/deepseek-ai/DeepSeek-V3-0324
wandb/deepseek-ai/DeepSeek-V3-0324
Wandb $1.14 $2.75 161,000 text
wandb/deepseek-ai/DeepSeek-V3.1
wandb/deepseek-ai/DeepSeek-V3.1
Wandb $0.5500 $1.65 161,000 text
wandb/deepseek-ai/DeepSeek-V4-Flash
wandb/deepseek-ai/DeepSeek-V4-Flash
Wandb $0.1400 $0.2800 $0.0700 1,048,576 text
wandb/deepseek-ai/DeepSeek-V4-Flash-0731
wandb/deepseek-ai/DeepSeek-V4-Flash-0731
Wandb $0.1300 $0.2800 $0.0700 262,144 text
wandb/deepseek-ai/DeepSeek-V4-Pro
wandb/deepseek-ai/DeepSeek-V4-Pro
Wandb $1.15 $2.55 $0.2000 1,048,576 text
wandb/deepseek-ai/DeepSeek-V4-Pro-0813
wandb/deepseek-ai/DeepSeek-V4-Pro-0813
Wandb $1.31 $3.96 $0.0440 text
wandb/google/gemma-4-31B-it
wandb/google/gemma-4-31B-it
Wandb $0.1000 $0.3400 262,144 text
wandb/ibm-granite/granite-4.1-8b
wandb/ibm-granite/granite-4.1-8b
Wandb $0.0500 $0.1000 131,072 text
wandb/ibm-granite/granite-4.2-8b
wandb/ibm-granite/granite-4.2-8b
Wandb $0.1000 $0.1500 $0.0500 text
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
Wandb $0.0500 $0.1000 131,072 text
wandb/meta-llama/Llama-3.1-70B-Instruct
wandb/meta-llama/Llama-3.1-70B-Instruct
Wandb $0.8000 $0.8000 128,000 text
wandb/meta-llama/Llama-3.1-8B-Instruct
wandb/meta-llama/Llama-3.1-8B-Instruct
Wandb $0.2200 $0.2200 128,000 text
wandb/meta-llama/Llama-3.3-70B-Instruct
wandb/meta-llama/Llama-3.3-70B-Instruct
Wandb $0.7100 $0.7100 128,000 text
wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct
wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct
Wandb $0.1700 $0.6600 64,000 text
wandb/microsoft/Phi-4-mini-instruct
wandb/microsoft/Phi-4-mini-instruct
Wandb $8,000.00 $35,000.00 128,000 text
wandb/MiniMaxAI/MiniMax-M2.5
wandb/MiniMaxAI/MiniMax-M2.5
Wandb $0.3000 $1.20 197,000 text
wandb/MiniMaxAI/MiniMax-M3
wandb/MiniMaxAI/MiniMax-M3
Wandb $0.2300 $0.9600 $0.0500 262,144 text
wandb/moonshotai/Kimi-K2-Instruct
wandb/moonshotai/Kimi-K2-Instruct
Wandb $0.6000 $2.50 128,000 text
wandb/moonshotai/Kimi-K2.5
wandb/moonshotai/Kimi-K2.5
Wandb $0.6000 $3.00 $0.1000 262,144 text
wandb/moonshotai/Kimi-K2.6
wandb/moonshotai/Kimi-K2.6
Wandb $0.6500 $3.41 $0.1500 262,144 text
wandb/moonshotai/Kimi-K2.7-Code
wandb/moonshotai/Kimi-K2.7-Code
Wandb $0.7100 $3.50 $0.1500 262,144 text
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Wandb $0.7500 $2.75 $0.1500 262,144 text
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Wandb $0.1000 $0.2500 $0.0500 262,144 text
wandb/openai/gpt-oss-120b
wandb/openai/gpt-oss-120b
Wandb $0.0300 $0.1700 131,072 text
wandb/openai/gpt-oss-20b
wandb/openai/gpt-oss-20b
Wandb $0.0300 $0.1300 131,072 text
wandb/OpenPipe/Qwen3-14B-Instruct
wandb/OpenPipe/Qwen3-14B-Instruct
Wandb $0.0500 $0.2200 32,768 text
wandb/Qwen/Qwen3-235B-A22B-Instruct-2507
wandb/Qwen/Qwen3-235B-A22B-Instruct-2507
Wandb $0.1000 $0.1000 262,144 text
wandb/Qwen/Qwen3-235B-A22B-Thinking-2507
wandb/Qwen/Qwen3-235B-A22B-Thinking-2507
Wandb $0.1000 $0.1000 262,144 text
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507
Wandb $0.1000 $0.3000 262,144 text
wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct
wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct
Wandb $1.00 $1.50 262,144 text
wandb/Qwen/Qwen3.5-35B-A3B
wandb/Qwen/Qwen3.5-35B-A3B
Wandb $0.2500 $1.25 262,144 text
wandb/Qwen/Qwen3.6-27B
wandb/Qwen/Qwen3.6-27B
Wandb $0.6000 $3.60 $0.1200 262,144 text
wandb/Qwen/Qwen3.6-35B-A3B
wandb/Qwen/Qwen3.6-35B-A3B
Wandb $0.2500 $1.25 262,144 text
wandb/Qwen/Qwen3.8-27B
wandb/Qwen/Qwen3.8-27B
Wandb $0.4000 $3.00 $0.1500 262,144 text
wandb/zai-org/GLM-4.5
wandb/zai-org/GLM-4.5
Wandb $55,000.00 $200,000.00 131,072 text
wandb/zai-org/GLM-5.2
wandb/zai-org/GLM-5.2
Wandb $0.7600 $2.42 $0.1400 262,144 text
watsonx/bigscience/mt0-xxl
watsonx/bigscience/mt0-xxl
Watsonx $1.91 $1.91 4,096 text
watsonx/bigscience/mt0-xxl-13b
watsonx/bigscience/mt0-xxl-13b
Watsonx $1.91 $1.91 4,096 text
watsonx/core42/jais-13b-chat
watsonx/core42/jais-13b-chat
Watsonx $500.00 $2,000.00 8,192 text
watsonx/google/flan-t5-xl-3b
watsonx/google/flan-t5-xl-3b
Watsonx $0.6000 $0.6000 8,192 text
watsonx/ibm/granite-13b-chat-v2
watsonx/ibm/granite-13b-chat-v2
Watsonx $0.6000 $0.6000 8,192 text
watsonx/ibm/granite-13b-instruct-v2
watsonx/ibm/granite-13b-instruct-v2
Watsonx $0.6000 $0.6000 8,192 text
watsonx/ibm/granite-3-3-8b-instruct
watsonx/ibm/granite-3-3-8b-instruct
Watsonx $0.2000 $0.2000 8,192 text
watsonx/ibm/granite-3-8b-instruct
watsonx/ibm/granite-3-8b-instruct
Watsonx $0.2000 $0.2000 8,192 text
watsonx/ibm/granite-4-h-small
watsonx/ibm/granite-4-h-small
Watsonx $0.0636 $0.2650 131,072 text
watsonx/ibm/granite-guardian-3-2-2b
watsonx/ibm/granite-guardian-3-2-2b
Watsonx $0.1000 $0.1000 8,192 text
watsonx/ibm/granite-guardian-3-3-8b
watsonx/ibm/granite-guardian-3-3-8b
Watsonx $0.2000 $0.2000 8,192 text
watsonx/ibm/granite-ttm-1024-96-r2
watsonx/ibm/granite-ttm-1024-96-r2
Watsonx $0.3800 $0.3800 512 text
watsonx/ibm/granite-ttm-1536-96-r2
watsonx/ibm/granite-ttm-1536-96-r2
Watsonx $0.3800 $0.3800 512 text
watsonx/ibm/granite-ttm-512-96-r2
watsonx/ibm/granite-ttm-512-96-r2
Watsonx $0.3800 $0.3800 512 text
watsonx/ibm/granite-vision-3-2-2b
watsonx/ibm/granite-vision-3-2-2b
Watsonx $0.1000 $0.1000 8,192 text
watsonx/meta-llama/llama-3-2-11b-vision-instruct
watsonx/meta-llama/llama-3-2-11b-vision-instruct
Watsonx $0.3500 $0.3500 128,000 text
watsonx/meta-llama/llama-3-2-1b-instruct
watsonx/meta-llama/llama-3-2-1b-instruct
Watsonx $0.1000 $0.1000 128,000 text
watsonx/meta-llama/llama-3-2-3b-instruct
watsonx/meta-llama/llama-3-2-3b-instruct
Watsonx $0.1500 $0.1500 128,000 text
watsonx/meta-llama/llama-3-2-90b-vision-instruct
watsonx/meta-llama/llama-3-2-90b-vision-instruct
Watsonx $2.00 $2.00 128,000 text
watsonx/meta-llama/llama-3-3-70b-instruct
watsonx/meta-llama/llama-3-3-70b-instruct
Watsonx $0.7526 $0.7526 131,072 text
watsonx/meta-llama/llama-4-maverick-17b
watsonx/meta-llama/llama-4-maverick-17b
Watsonx $0.3710 $1.48 131,072 text
watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Watsonx $0.3710 $1.48 131,072 text
watsonx/meta-llama/llama-guard-3-11b-vision
watsonx/meta-llama/llama-guard-3-11b-vision
Watsonx $0.3500 $0.3500 128,000 text
watsonx/mistralai/mistral-large
watsonx/mistralai/mistral-large
Watsonx $3.00 $10.00 131,072 text
watsonx/mistralai/mistral-medium-2505
watsonx/mistralai/mistral-medium-2505
Watsonx $3.00 $10.00 128,000 text
watsonx/mistralai/mistral-small-2503
watsonx/mistralai/mistral-small-2503
Watsonx $0.1000 $0.3000 32,000 text
watsonx/mistralai/mistral-small-3-1-24b-instruct-2503
watsonx/mistralai/mistral-small-3-1-24b-instruct-2503
Watsonx $0.1060 $0.3180 131,072 text
watsonx/mistralai/pixtral-12b-2409
watsonx/mistralai/pixtral-12b-2409
Watsonx $0.3500 $0.3500 128,000 text
watsonx/openai/gpt-oss-120b
watsonx/openai/gpt-oss-120b
Watsonx $0.1590 $0.6360 131,072 text
watsonx/sdaia/allam-1-13b-instruct
watsonx/sdaia/allam-1-13b-instruct
Watsonx $1.80 $1.80 8,192 text
xai/grok-2
xai/grok-2
xAI $2.00 $10.00 131,072 text
xai/grok-2-1212
xai/grok-2-1212
xAI $2.00 $10.00 131,072 text
xai/grok-2-latest
xai/grok-2-latest
xAI $2.00 $10.00 131,072 text
xai/grok-2-vision
xai/grok-2-vision
xAI $2.00 $10.00 32,768 text

Prices are sourced from the open LiteLLM dataset and may lag provider changes. Always confirm against the provider's official pricing before relying on a figure.